NUMERICAL SIMULATION OF NEURAL NETWORKS WITH TRANSLATION AND ROTATION INVARIANT PATTERN RECOGNITION

Publisher Website
Google Scholar
Abstract
A Hopfield-like network modified for translation and rotation invariant pattern recognition is studied on a computer. The neural firing thresholds θ are used as additional degrees of freedom. The phase diagram in the space of parameters (T, θ) is obtained both for the translation and the rotation.

This publication has 0 references indexed in Scilit: